spidy 0.2.4 → 0.2.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/spidy.rb +4 -0
- data/lib/spidy/binder.rb +0 -4
- data/lib/spidy/connector.rb +31 -3
- data/lib/spidy/connector/direct.rb +5 -2
- data/lib/spidy/connector/html.rb +43 -57
- data/lib/spidy/connector/json.rb +11 -3
- data/lib/spidy/connector/xml.rb +7 -3
- data/lib/spidy/console.rb +5 -0
- data/lib/spidy/definition.rb +14 -2
- data/lib/spidy/version.rb +1 -1
- data/spidy.gemspec +1 -0
- metadata +20 -6
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: f123b0f2bb611ea41bafe6a9cb5a7bb7564ba6be7044127e77fddf34dc3faed1
|
4
|
+
data.tar.gz: 87f0079575c62dac9a43d6900b88da45cce77a37f5b994376b0d31dd24b03fa5
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b6554befde64315d01d2db11ba22b479629ae602ca4acddee51c941bd091144849ad15f2b98c220d29bd97c70c02fc2726061db429db2140a50bbfe0fce850a2
|
7
|
+
data.tar.gz: 511b7dccf5f93e4cf8a652d3039ec852c556cbd49e238c676029d1b0e611dce669ac84140c8b9be3f861426e8f248f6452698bf7319f5493cb7ecccb3cd1428d
|
data/lib/spidy.rb
CHANGED
@@ -4,6 +4,7 @@ require 'spidy/version'
|
|
4
4
|
require 'active_support/all'
|
5
5
|
require 'mechanize'
|
6
6
|
require 'open-uri'
|
7
|
+
require 'socksify'
|
7
8
|
|
8
9
|
#
|
9
10
|
# web spider dsl engine
|
@@ -36,6 +37,9 @@ module Spidy
|
|
36
37
|
spidy.instance_eval do
|
37
38
|
undef :spider
|
38
39
|
undef :define
|
40
|
+
undef :wait_time
|
41
|
+
undef :user_agent
|
42
|
+
undef :socks_proxy
|
39
43
|
end
|
40
44
|
spidy
|
41
45
|
end
|
data/lib/spidy/binder.rb
CHANGED
data/lib/spidy/connector.rb
CHANGED
@@ -10,6 +10,24 @@ module Spidy::Connector
|
|
10
10
|
autoload :Json
|
11
11
|
autoload :Xml
|
12
12
|
|
13
|
+
#
|
14
|
+
# retry class
|
15
|
+
#
|
16
|
+
class Retry < StandardError
|
17
|
+
attr_reader :page
|
18
|
+
attr_reader :response_code
|
19
|
+
attr_reader :wait_time
|
20
|
+
|
21
|
+
def initialize(wait_time: 2, page: nil, error: nil)
|
22
|
+
@page = page
|
23
|
+
@wait_time = wait_time
|
24
|
+
@response_code = error.try(:response_code) || page.try(:response_code)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
#
|
29
|
+
# default user agent
|
30
|
+
#
|
13
31
|
USER_AGENT = [
|
14
32
|
'Mozilla/5.0',
|
15
33
|
'(Macintosh; Intel Mac OS X 10_12_6)',
|
@@ -19,9 +37,19 @@ module Spidy::Connector
|
|
19
37
|
'Safari/537.36'
|
20
38
|
].join(' ')
|
21
39
|
|
22
|
-
|
23
|
-
|
40
|
+
#
|
41
|
+
# get connection handller
|
42
|
+
#
|
43
|
+
def self.get(value, wait_time: nil, user_agent: nil, socks_proxy: nil)
|
44
|
+
return value if value.respond_to?(:call)
|
45
|
+
|
46
|
+
connector = const_get(value.to_s.classify).new(wait_time: wait_time || 5, user_agent: user_agent || USER_AGENT)
|
47
|
+
return connector if socks_proxy.nil?
|
24
48
|
|
25
|
-
|
49
|
+
lambda do |url, &block|
|
50
|
+
Socksify::proxy(socks_proxy[:host], socks_proxy[:port]) do
|
51
|
+
connector.call(url, &block)
|
52
|
+
end
|
53
|
+
end
|
26
54
|
end
|
27
55
|
end
|
@@ -3,8 +3,11 @@
|
|
3
3
|
#
|
4
4
|
# Direct resource ( not network resource )
|
5
5
|
#
|
6
|
-
|
7
|
-
def
|
6
|
+
class Spidy::Connector::Direct
|
7
|
+
def call(resource, &yielder)
|
8
8
|
yielder.call(resource)
|
9
9
|
end
|
10
|
+
|
11
|
+
def initialize(wait_time: nil, user_agent: nil)
|
12
|
+
end
|
10
13
|
end
|
data/lib/spidy/connector/html.rb
CHANGED
@@ -3,74 +3,60 @@
|
|
3
3
|
#
|
4
4
|
# Mechanize wrapper
|
5
5
|
#
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
attr_reader :wait_time
|
14
|
-
|
15
|
-
def initialize(wait_time: 2, page: nil, error: nil)
|
16
|
-
@page = page
|
17
|
-
@wait_time = wait_time
|
18
|
-
@response_code = error.try(:response_code) || page.try(:response_code)
|
19
|
-
end
|
6
|
+
class Spidy::Connector::Html
|
7
|
+
def initialize(wait_time:, user_agent:, logger: nil)
|
8
|
+
@wait_time = wait_time
|
9
|
+
@logger = logger || proc { |values| STDERR.puts(values.to_json) }
|
10
|
+
@agent = Mechanize.new
|
11
|
+
@user_agent = user_agent
|
12
|
+
@agent.user_agent = user_agent
|
20
13
|
end
|
21
14
|
|
22
|
-
|
23
|
-
|
24
|
-
@agent.user_agent = Spidy::Connector::USER_AGENT
|
25
|
-
|
26
|
-
class << self
|
27
|
-
attr_reader :agent
|
28
|
-
attr_accessor :logger
|
15
|
+
attr_reader :agent
|
16
|
+
attr_reader :logger
|
29
17
|
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
end
|
36
|
-
logger.call('connnector.get': url, 'connnector.accessed': Time.current)
|
37
|
-
get(url, retry_count, yielder)
|
18
|
+
def call(url, encoding: nil, retry_count: 5, &yielder)
|
19
|
+
fail 'url is not specified' if url.blank?
|
20
|
+
if encoding
|
21
|
+
agent.default_encoding = encoding
|
22
|
+
agent.force_default_encoding = true
|
38
23
|
end
|
24
|
+
logger.call('connnector.get': url, 'connnector.accessed': Time.current)
|
25
|
+
get(url, retry_count, yielder)
|
26
|
+
end
|
39
27
|
|
40
|
-
|
28
|
+
private
|
41
29
|
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
30
|
+
def get(url, retry_count, yielder)
|
31
|
+
connect(url, retry_count, yielder)
|
32
|
+
rescue Spidy::Connector::Retry => e
|
33
|
+
logger.call('retry.accessed': Time.current,
|
34
|
+
'retry.uri': url,
|
35
|
+
'retry.response_code': e.response_code,
|
36
|
+
'retry.rest_count': retry_count)
|
49
37
|
|
50
|
-
|
51
|
-
|
38
|
+
@agent = Mechanize.new
|
39
|
+
@agent.user_agent = @user_agent
|
52
40
|
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
end
|
58
|
-
raise e
|
41
|
+
retry_count -= 1
|
42
|
+
if retry_count.positive?
|
43
|
+
sleep e.wait_time
|
44
|
+
retry
|
59
45
|
end
|
46
|
+
raise e
|
47
|
+
end
|
60
48
|
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
49
|
+
def connect(url, retry_count, yielder)
|
50
|
+
result = nil
|
51
|
+
agent.get(url) do |page|
|
52
|
+
fail Spidy::Connector::Retry, page: page, wait_time: @wait_time if page.title == 'Sorry, unable to access page...'
|
65
53
|
|
66
|
-
|
67
|
-
end
|
68
|
-
result
|
69
|
-
rescue Mechanize::ResponseCodeError => e
|
70
|
-
raise Retry, error: e if e.response_code == '429'
|
71
|
-
raise Retry, error: e if e.response_code == '502'
|
72
|
-
raise e
|
54
|
+
result = yielder.call(page)
|
73
55
|
end
|
74
|
-
|
56
|
+
result
|
57
|
+
rescue Mechanize::ResponseCodeError => e
|
58
|
+
raise Spidy::Connector::Retry, error: e, wait_time: @wait_time if e.response_code == '429'
|
59
|
+
raise Spidy::Connector::Retry, error: e, wait_time: @wait_time if e.response_code == '502'
|
60
|
+
raise e
|
75
61
|
end
|
76
62
|
end
|
data/lib/spidy/connector/json.rb
CHANGED
@@ -3,9 +3,17 @@
|
|
3
3
|
#
|
4
4
|
# OpenURI to JSON.parse
|
5
5
|
#
|
6
|
-
|
7
|
-
def
|
6
|
+
class Spidy::Connector::Json
|
7
|
+
def initialize(wait_time: nil, user_agent: nil)
|
8
|
+
@user_agent = user_agent
|
9
|
+
end
|
10
|
+
|
11
|
+
def call(url, &block)
|
8
12
|
fail 'url is not specified' if url.blank?
|
9
|
-
|
13
|
+
connect(url, &block)
|
14
|
+
end
|
15
|
+
|
16
|
+
def connect(url)
|
17
|
+
OpenURI.open_uri(url, "User-Agent" => @user_agent) { |body| yield JSON.parse(body.read, symbolize_names: true) }
|
10
18
|
end
|
11
19
|
end
|
data/lib/spidy/connector/xml.rb
CHANGED
@@ -3,12 +3,16 @@
|
|
3
3
|
#
|
4
4
|
# xml
|
5
5
|
#
|
6
|
-
|
7
|
-
def
|
6
|
+
class Spidy::Connector::Xml
|
7
|
+
def call(url)
|
8
8
|
fail 'URL is undefined' if url.blank?
|
9
9
|
|
10
|
-
OpenURI.open_uri(url, "User-Agent" =>
|
10
|
+
OpenURI.open_uri(url, "User-Agent" => @user_agent) do |body|
|
11
11
|
yield Nokogiri::XML(body.read.gsub(/[\x00-\x09\x0B\x0C\x0E-\x1F\x7F]/, ''), url)
|
12
12
|
end
|
13
13
|
end
|
14
|
+
|
15
|
+
def initialize(wait_time: nil, user_agent: nil)
|
16
|
+
@user_agent = user_agent
|
17
|
+
end
|
14
18
|
end
|
data/lib/spidy/console.rb
CHANGED
data/lib/spidy/definition.rb
CHANGED
@@ -16,6 +16,18 @@ module Spidy::Definition
|
|
16
16
|
spidy.call(source, &yielder)
|
17
17
|
end
|
18
18
|
|
19
|
+
def user_agent(user_agent)
|
20
|
+
@user_agent = user_agent
|
21
|
+
end
|
22
|
+
|
23
|
+
def wait_time(wait_time)
|
24
|
+
@wait_time = wait_time
|
25
|
+
end
|
26
|
+
|
27
|
+
def socks_proxy(host, port)
|
28
|
+
@socks_proxy = { host: host, port: port }
|
29
|
+
end
|
30
|
+
|
19
31
|
def each(source = nil, name: :default, &yielder)
|
20
32
|
name = name.presence || :default
|
21
33
|
spidy = @namespace[:"#{name}_spider"]
|
@@ -26,7 +38,7 @@ module Spidy::Definition
|
|
26
38
|
|
27
39
|
def spider(name = :default, connector: nil, as: nil, &define_block)
|
28
40
|
@namespace ||= {}
|
29
|
-
connector = Spidy::Connector.get(connector || as)
|
41
|
+
connector = Spidy::Connector.get(connector || as, wait_time: @wait_time, user_agent: @user_agent, socks_proxy: @socks_proxy)
|
30
42
|
@namespace[:"#{name}_spider"] = proc do |source, &yielder|
|
31
43
|
define_block.call(yielder, connector, source)
|
32
44
|
end
|
@@ -34,7 +46,7 @@ module Spidy::Definition
|
|
34
46
|
|
35
47
|
def define(name = :default, connector: nil, binder: nil, as: nil, &define_block)
|
36
48
|
@namespace ||= {}
|
37
|
-
connector = Spidy::Connector.get(connector || as)
|
49
|
+
connector = Spidy::Connector.get(connector || as, wait_time: @wait_time, user_agent: @user_agent)
|
38
50
|
binder = Spidy::Binder.get(self, binder || as)
|
39
51
|
@namespace[:"#{name}_scraper"] = define_proc(name, connector, binder, define_block)
|
40
52
|
end
|
data/lib/spidy/version.rb
CHANGED
data/spidy.gemspec
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: spidy
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- aileron
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-
|
11
|
+
date: 2020-08-31 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -122,6 +122,20 @@ dependencies:
|
|
122
122
|
- - ">="
|
123
123
|
- !ruby/object:Gem::Version
|
124
124
|
version: '0'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: socksify
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - ">="
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '0'
|
132
|
+
type: :runtime
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - ">="
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '0'
|
125
139
|
- !ruby/object:Gem::Dependency
|
126
140
|
name: pry
|
127
141
|
requirement: !ruby/object:Gem::Requirement
|
@@ -136,7 +150,7 @@ dependencies:
|
|
136
150
|
- - ">="
|
137
151
|
- !ruby/object:Gem::Version
|
138
152
|
version: '0'
|
139
|
-
description:
|
153
|
+
description:
|
140
154
|
email:
|
141
155
|
- aileron.cc@gmail.com
|
142
156
|
executables:
|
@@ -183,7 +197,7 @@ homepage: https://github.com/aileron-inc/spidy
|
|
183
197
|
licenses:
|
184
198
|
- MIT
|
185
199
|
metadata: {}
|
186
|
-
post_install_message:
|
200
|
+
post_install_message:
|
187
201
|
rdoc_options: []
|
188
202
|
require_paths:
|
189
203
|
- lib
|
@@ -199,7 +213,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
199
213
|
version: '0'
|
200
214
|
requirements: []
|
201
215
|
rubygems_version: 3.0.3
|
202
|
-
signing_key:
|
216
|
+
signing_key:
|
203
217
|
specification_version: 4
|
204
218
|
summary: web spider dsl
|
205
219
|
test_files: []
|